Comparing machine translation and human translation for South African languages

Abstract

Machine translation (MT) has been available for several years but has only recently begun to be considered viable, particularly in the context of indigenous South African languages. Although the quality of an MT remains inferior to that of a human translation (HT), MT systems have gained popularity, making some significant contributions to translation studies. This study explored the similarities and differences between the two modes of translation. A case study approach based on a qualitative research method was used. The source data for this study are an  MT and an HT of an article titled “Stellenbosch University to offer academic and psychosocial support to students”, written by Ntwaagae Seleka and published on News24. As a computer-aided translation tool, Autshumato Machine Translation Web Service (MTWS) produced the MT from English into Setswana as a target text. Meanwhile, a Setswana master’s student from the Tshwane University of Technology manually translated the source text. The findings show that the human translator outperformed the MTWS in providing high-quality translation. The MTWS was unable to offer a better translation in terms of case sensitivity and terminological inconsistencies. It also mistranslated, adding and omitting words that changed the intended meaning and leaving certain words untranslated. Human cognitive competency, intelligence, and flexibility enable human translators to deal with such translation problems to provide high-quality outputs. The initiatives discussed in this study show that even though the MTWS operates as a useful translation tool with the capacity to instantly translate a large number of documents, its output is not yet capable of replacing an HT when translating into indigenous South African languages. Post-editing of the MTWS outputs is always recommended.